mirror of
git://sourceware.org/git/glibc.git
synced 2024-12-09 04:11:27 +08:00
5062680c60
This patch converts asm statements into builtins for AArch64. As an example for the file sysdeps/aarch64/fpu/s_ceil.c, we convert the function from double __ceil (double x) { double result; asm ("frintp\t%d0, %d1" : "=w" (result) : "w" (x) ); return result; } into double __ceil (double x) { return __builtin_ceil (x); } Tested on aarch64-linux-gnu with gcc-4.9.4 and gcc-6. * sysdeps/aarch64/fpu/e_sqrt.c (ieee754_sqrt): Replace asm statements with __builtin_sqrt. * sysdeps/aarch64/fpu/e_sqrtf.c (ieee754_sqrtf): Replace asm statements with __builtin_sqrtf. * sysdeps/aarch64/fpu/s_ceil.c (__ceil): Replace asm statements with __builtin_ceil. * sysdeps/aarch64/fpu/s_ceilf.c (__ceilf): Replace asm statements with __builtin_ceilf. * sysdeps/aarch64/fpu/s_floor.c (__floor): Replace asm statements with __builtin_floor. * sysdeps/aarch64/fpu/s_floorf.c (__floorf): Replace asm statements with __builtin_floorf. * sysdeps/aarch64/fpu/s_fma.c (__fma): Replace asm statements with __builtin_fma. * sysdeps/aarch64/fpu/s_fmaf.c (__fmaf): Replace asm statements with __builtin_fmaf. * sysdeps/aarch64/fpu/s_fmax.c (__fmax): Replace asm statements with __builtin_fmax. * sysdeps/aarch64/fpu/s_fmaxf.c (__fmaxf): Replace asm statements with __builtin_fmaxf. * sysdeps/aarch64/fpu/s_fmin.c (__fmin): Replace asm statements with __builtin_fmin. * sysdeps/aarch64/fpu/s_fminf.c (__fminf): Replace asm statements with __builtin_fminf. * sysdeps/aarch64/fpu/s_frint.c: Delete file. * sysdeps/aarch64/fpu/s_frintf.c: Delete file. * sysdeps/aarch64/fpu/s_llrint.c (__llrint): Replace asm statements with builtin_rint and conversion to int. * sysdeps/aarch64/fpu/s_llrintf.c (__llrintf): Likewise. * sysdeps/aarch64/fpu/s_llround.c (__llround): Replace asm statements with builtin_llround. * sysdeps/aarch64/fpu/s_llroundf.c (__llroundf): Likewise. * sysdeps/aarch64/fpu/s_lrint.c (__lrint): Replace asm statements with builtin_rint and conversion to long int. * sysdeps/aarch64/fpu/s_lrintf.c (__lrintf): Likewise. * sysdeps/aarch64/fpu/s_lround.c (__lround): Replace asm statements with builtin_lround. * sysdeps/aarch64/fpu/s_lroundf.c (__lroundf): Replace asm statements with builtin_lroundf. * sysdeps/aarch64/fpu/s_nearbyint.c (__nearbyint): Replace asm statements with __builtin_nearbyint. * sysdeps/aarch64/fpu/s_nearbyintf.c (__nearbyintf): Replace asm statements with __builtin_nearbyintf. * sysdeps/aarch64/fpu/s_rint.c (__rint): Replace asm statements with __builtin_rint. * sysdeps/aarch64/fpu/s_rintf.c (__rintf): Replace asm statements with __builtin_rintf. * sysdeps/aarch64/fpu/s_round.c (__round): Replace asm statements with __builtin_round. * sysdeps/aarch64/fpu/s_roundf.c (__roundf): Replace asm statements with __builtin_roundf. * sysdeps/aarch64/fpu/s_trunc.c (__trunc): Replace asm statements with __builtin_trunc. * sysdeps/aarch64/fpu/s_truncf.c (__truncf): Replace asm statements with __builtin_truncf. * sysdeps/aarch64/fpu/Makefile: Build e_sqrt[f].c with -fno-math-errno.
88 lines
2.2 KiB
C
88 lines
2.2 KiB
C
/* Copyright (C) 1996-2017 Free Software Foundation, Inc.
|
|
|
|
This file is part of the GNU C Library.
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
modify it under the terms of the GNU Lesser General Public
|
|
License as published by the Free Software Foundation; either
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
The GNU C Library is distributed in the hope that it will be useful,
|
|
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
|
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
|
Lesser General Public License for more details.
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
License along with the GNU C Library; if not, see
|
|
<http://www.gnu.org/licenses/>. */
|
|
|
|
#include <math.h>
|
|
#include <get-rounding-mode.h>
|
|
#include <stdint.h>
|
|
#include <math_private.h>
|
|
|
|
# define IREG_SIZE 64
|
|
|
|
# ifdef __ILP32__
|
|
# define OREG_SIZE 32
|
|
# else
|
|
# define OREG_SIZE 64
|
|
# endif
|
|
|
|
# define IREGS "d"
|
|
|
|
#if OREG_SIZE == 32
|
|
# define OREGS "w"
|
|
#else
|
|
# define OREGS "x"
|
|
#endif
|
|
|
|
|
|
long int
|
|
__lrint (double x)
|
|
{
|
|
|
|
#if IREG_SIZE == 64 && OREG_SIZE == 32
|
|
long int result;
|
|
|
|
if (__builtin_fabs (x) > INT32_MAX)
|
|
{
|
|
/* Converting large values to a 32 bit int may cause the frintx/fcvtza
|
|
sequence to set both FE_INVALID and FE_INEXACT. To avoid this
|
|
check the rounding mode and do a single instruction with the
|
|
appropriate rounding mode. */
|
|
|
|
switch (get_rounding_mode ())
|
|
{
|
|
case FE_TONEAREST:
|
|
asm volatile ("fcvtns" "\t%" OREGS "0, %" IREGS "1"
|
|
: "=r" (result) : "w" (x));
|
|
break;
|
|
case FE_UPWARD:
|
|
asm volatile ("fcvtps" "\t%" OREGS "0, %" IREGS "1"
|
|
: "=r" (result) : "w" (x));
|
|
break;
|
|
case FE_DOWNWARD:
|
|
asm volatile ("fcvtms" "\t%" OREGS "0, %" IREGS "1"
|
|
: "=r" (result) : "w" (x));
|
|
break;
|
|
case FE_TOWARDZERO:
|
|
default:
|
|
asm volatile ("fcvtzs" "\t%" OREGS "0, %" IREGS "1"
|
|
: "=r" (result) : "w" (x));
|
|
}
|
|
return result;
|
|
}
|
|
#endif
|
|
|
|
double r = __builtin_rint (x);
|
|
|
|
/* Prevent gcc from calling lrint directly when compiled with
|
|
-fno-math-errno by inserting a barrier. */
|
|
|
|
math_opt_barrier (r);
|
|
return r;
|
|
}
|
|
|
|
weak_alias (__lrint, lrint)
|